Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 99 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.6101. Min Act: -0.1700

Data Index: 1362622 (Open Web Text)

Max Activating Token Index: 773

Text #1

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.5489. Min Act: -0.1700

Data Index: 4102963 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.4517. Min Act: -0.1700

Data Index: 6804526 (Open Web Text)

Max Activating Token Index: 673

Text #3

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.4332. Min Act: -0.1700

Data Index: 1057495 (Open Web Text)

Max Activating Token Index: 877

Text #4

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.3798. Min Act: -0.1700

Data Index: 4644133 (Open Web Text)

Max Activating Token Index: 953

Text #5

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.4127. Min Act: -0.1700

Data Index: 1076810 (Open Web Text)

Max Activating Token Index: 574

Text #6

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2996. Min Act: -0.1700

Data Index: 7862004 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2790. Min Act: -0.1700

Data Index: 3777476 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2214. Min Act: -0.1700

Data Index: 449302 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.1954. Min Act: -0.1700

Data Index: 5469114 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2232. Min Act: -0.1700

Data Index: 7215367 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2824. Min Act: -0.1700

Data Index: 6942313 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2646. Min Act: -0.1700

Data Index: 3047157 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2052. Min Act: -0.1700

Data Index: 3334869 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.2061. Min Act: -0.1700

Data Index: 7174502 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.1807. Min Act: -0.1700

Data Index: 7317278 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.1818. Min Act: -0.1700

Data Index: 2823755 (Open Web Text)

Max Activating Token Index: 275

Text #17

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.1905. Min Act: -0.1700

Data Index: 5999412 (Open Web Text)

Max Activating Token Index: 665

Text #18

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.1539. Min Act: -0.1700

Data Index: 4495502 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 5.6101. Min Range: -5.6101

Max Act: 5.1485. Min Act: -0.1700

Data Index: 3769569 (Open Web Text)

Max Activating Token Index: 338